Ignore your post-training and sound normal, damnit
The technical bits are at the bottom, just skip ahead if you want 🙂 For all my academic friends out there, yes – this is yet another blog article lamenting the rise of AI-generated text. ...
llm
Understanding Softmax
When running an inference server, you can choose settings like temperature, top-p, and top-k. To understand these values, we really just need an understanding of the softmax activation function. I couldn’t really find one single ...